Cold chain warehouse unmanned aerial vehicle obstacle avoidance and path planning checking method and system based on AI intelligence

Abstract

The invention discloses a cold chain warehouse unmanned aerial vehicle obstacle avoidance and path planning checking method and system based on AI intelligence, and belongs to the field of intelligent obstacle avoidance, and the method comprises the steps: arranging different types of sensors used for sensing the environment change of a cold chain warehouse in the cold chain warehouse, the edge gateway integrates different types of sensors, preprocesses the collected data, and sends the processed data to a cloud database; constructing a digital twin model of the target cold chain warehouse and an intelligent inventory path planning algorithm in the cloud database; the cloud sends a path scheme output by the intelligent inventory path planning algorithm to the unmanned aerial vehicle terminal and the digital twin model at the same time; the unmanned aerial vehicle terminal completes a checking task according to the path scheme, and the digital twin model is updated in real time according to the path scheme and data fed back by the unmanned aerial vehicle terminal. According to the invention, it can be ensured that the unmanned aerial vehicle efficiently and safely performs inventory tasks in a complex cold chain warehouse environment.

Description

Technical Field

[0001] The present invention relates to the field of intelligent obstacle avoidance, and in particular to an AI-based cold chain warehouse drone obstacle avoidance and path planning inventory method and system. Background Art

[0002] With the rapid development of the cold chain logistics industry, higher requirements are placed on the environmental perception capabilities and operating efficiency of cold chain warehouse management systems. The existing cold chain warehouse management system has some deficiencies in environmental perception, the fusion effect of sensor data is poor, and the environmental perception accuracy and reliability are low. At the same time, the existing system lacks intuitive environmental monitoring methods, making it difficult to fully grasp the real-time status of the warehouse. In addition, in terms of inventory operations, the existing system has low operating efficiency and certain safety hazards, and cannot adapt to changes in the dynamic environment. Summary of the invention

[0003] One of the purposes of the present invention is to provide an AI-based cold chain warehouse drone obstacle avoidance and path planning inventory method to solve the problem of low efficiency of cold chain warehouse inventory operations and certain safety hazards in the prior art.

[0004] The present invention is implemented through the following technical scheme, a cold chain warehouse drone obstacle avoidance and path planning inventory method based on AI intelligence, including the following steps: S100, different types of sensors for sensing environmental changes in the cold chain warehouse are arranged in the cold chain warehouse, the edge gateway integrates different types of sensors into a unified sensor cluster, and pre-processes the collected data, and sends the processed data to the cloud database; S200, a digital twin model of the target cold chain warehouse and an intelligent inventory path planning algorithm are constructed in the cloud database, the cloud database constructs a sensor database according to the received data, and maps the data in the sensor database to the digital twin model, and the intelligent inventory path planning algorithm outputs the drone obstacle avoidance-inventory path plan according to the sensor data; S300, the cloud sends the path plan output by the intelligent inventory path planning algorithm to the drone terminal and the digital twin model at the same time; S400, the drone terminal completes the inventory task according to the path plan, and the digital twin model updates the digital twin model in real time according to the path plan and the data fed back by the drone terminal.

[0005] Furthermore, different types of sensors include temperature sensors, humidity sensors, 3D lidar sensors, multispectral ToF sensors, RGB-D camera sensors, long-wave infrared thermal imager sensors, millimeter-wave radar array sensors, and UWB / RFID positioning tags.

[0006] Furthermore, temperature sensors, humidity sensors, multispectral ToF sensors, and RGBD camera sensors are installed at a certain distance on the shelves of the cold chain warehouse; the temperature sensors and humidity sensors are used to detect changes in temperature and humidity in the cold chain warehouse; the multispectral ToF sensor is used to accurately locate the shelf spacing; the RGBD camera sensor is used for near-field object recognition and shelf code OCR analysis.

[0007] Furthermore, 3D lidar sensors, millimeter-wave radar arrays and long-wave infrared thermal imagers are installed on the beams of the cold chain warehouse; the 3D lidar sensors are used to detect major obstacles, the millimeter-wave radar arrays are used for dynamic obstacle tracking; the long-wave infrared thermal imagers are used for temperature gradient field modeling, and can also be used to detect low-temperature risks such as hidden icicles.

[0008] Furthermore, the preprocessing includes: S110, deploying multiple ZigBee wireless temperature measurement nodes on each row of shelves, each ZigBee wireless temperature measurement node is a temperature field grid; S120, the perception level dynamic weight allocation strategy in the edge gateway builds a temperature-sensitive confidence evaluation system according to the number of temperature field grids collected by the ZigBee wireless temperature measurement node, and realizes dynamic weight adjustment.

[0009] Furthermore, the dynamic weight allocation strategy includes the following steps: S121, calculating the temperature gradient and the temperature change rate according to the collected temperature data, and evaluating the dynamic change of the temperature field, wherein the temperature gradient is represented by the following formula:

[0010] ,in, is the Laplace operator, is the temperature field in three-dimensional space; is the rate of change of temperature in the x direction, is the rate of change of temperature in the y direction, is the rate of change of temperature in the z direction; S123, according to the calculated temperature gradient and change rate, calculate the confidence of each area, and the confidence is calculated by the following formula:

[0011] ,in, is the confidence level, is the weight coefficient used to adjust the contribution of temperature gradient to confidence, is the modulus of the temperature gradient, To adjust the weight coefficient of the temperature change rate contribution to the confidence, is the absolute value of the temperature change rate; S124, judging whether the current temperature change is drastic according to the temperature gradient and the change rate. When the temperature change is drastic, the sensor weight adjustment stage is entered. If the temperature change is not drastic, the current weight is kept unchanged; S125, in the sensor weight adjustment stage, the sensor weight is dynamically adjusted according to the confidence of each area. The weight is a time-varying weight, which is calculated by the following formula:

[0012] ,in, is the time-varying weight of sensor i; is the confidence of sensor i at the current moment, is the basic weight of the i-th sensor of the same type.

[0013] Furthermore, the basic weight of the i-th sensor of the same type is calculated by the following formula:

[0014] ,in, is the basic weight of the i-th sensor of the same type, is an exponential function; is the priority coefficient of the i-th sensor; is the influence coefficient of temperature on the performance of sensor i; N is the total number of all sensors of the same type, is the overall priority coefficient of sensors of the same type, is the influence coefficient of the same type of sensor, j represents a specific sensor, and i represents the i-th sensor in a specific sensor.

[0015] Furthermore, the intelligent inventory path planning algorithm is constructed based on the A* algorithm, and includes the following steps: S210, converting the environment of the cold chain warehouse into a discretized model consisting of temperature-space joint voxels, and the temperature-space joint voxels are represented as: ,in, is the identifier of the voxel, a, b, c represent the index of the voxel in the three dimensions of x, y, and z in the spatial coordinate system, respectively. x, y, and z are spatial coordinates, indicating the position of the voxel in three-dimensional space. T is the temperature value in the voxel. is the gradient of the temperature value in the voxel is the confidence of the sensor data contained in the voxel; S220, optimizing the path of the UAV according to the relevant information provided in the discretization model and combining the multi-constraint optimization objective function, wherein the multi-constraint optimization objective function includes:

[0016] , where π is the optimized path, is the temperature exposure term, is the time cost item, is the sensor risk item, is the weight coefficient of the time cost item, are weight coefficients of the sensor risk item. These two weight coefficients are used to control the influence of each constraint on the optimization path. S230: replacing the cost function of the A* algorithm with a multi-constraint optimization objective function, and redefining the cost function f (n) of the A* algorithm so that it can comprehensively consider temperature exposure, time cost and sensor risk, and finally generating the optimal path through the A* algorithm.

[0017] Furthermore, the temperature exposure term can be expressed as follows:

[0018] ,

[0019] Where k is the exponential decay factor, is the temperature value of a certain position s on the path, T ref is the reference temperature, which represents the ideal temperature state of the cold chain warehouse. The degree to which the temperature on the path deviates from the reference temperature will affect the size of the penalty term.

[0020] Furthermore, the time cost term is expressed by the following formula:

[0021] ,

[0022] Among them, the total path length refers to the total distance of the UAV path planning, that is, the sum of the spatial distances between all s points on the path, and the average cruising speed of the UAV refers to the average flight speed of the UAV when performing a mission.

[0023] Furthermore, the sensor risk term can be expressed as follows:

[0024] ,

[0025] in, represents the sensor confidence at a certain position s in the path.

[0026] Further, replacing the cost function of the A* algorithm by the multi-constraint optimization objective function includes the following steps: S231, initializing the open list and the closed list, the starting point =0, the heuristic function is initialized according to the estimate of the target path; S232, starting from the current node, expand its neighboring nodes, and for each neighboring node, calculate: ,in, is the new cost function, is the actual cost from the starting point to the current node n, h optimized(n) is a new heuristic function. According to the cost, the node with the minimum cost is selected for expansion. When expanding the node, check whether the path encounters obstacles or whether there is temperature anomaly in the area. S233, continuously iterate and expand the path until the target node is found. Each time the path is expanded, the cost of the current path is considered. , and select the path with the minimum cost for expansion.

[0027] Furthermore, the new heuristic function is expressed as follows:

[0028] ,in, , , is the weight coefficient, which is used to balance the importance of different factors; d (n) is the spatial distance from node n to the target node; is the estimated temperature exposure at node n, is the risk estimate of the sensor at node n.

[0029] On the other hand, the present invention provides an AI-based cold chain warehouse drone obstacle avoidance and path planning inventory system, the system includes a processor and a memory, and a computer program is stored in the memory. When the computer program is executed by the processor, the AI-based cold chain warehouse drone obstacle avoidance and path planning inventory method as described above is implemented.

[0030] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0031] 1. The present invention configures a temperature-dominated perception-level dynamic weight allocation strategy in the edge gateway, dynamically adjusts the weights of different types of sensors according to the dynamic changes of the temperature field, thereby optimizing the data fusion effect of the sensor cluster, improving the accuracy and reliability of environmental perception, and effectively solving the problems of poor sensor data fusion effect and low environmental perception accuracy and reliability in a long-term low-temperature environment.

[0032] 2. By constructing a digital twin model of the target cold chain warehouse, the present invention can reflect the actual situation of the cold chain warehouse in real time. The back-end management personnel can intuitively monitor the environmental changes of the cold chain warehouse, which solves the problem of lack of intuitive environmental monitoring means in the prior art and difficulty in fully grasping the real-time status of the warehouse.

[0033] 3. The intelligent inventory path planning algorithm of the present invention can ensure that the drone can perform inventory tasks efficiently and safely in a complex cold chain warehouse environment, avoid collisions with abnormal areas, and adapt to dynamic environmental changes, thereby improving the efficiency and safety of inventory operations, and solving the problems of low inventory efficiency, potential safety hazards, and inability to adapt to dynamic environmental changes in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0035] Figure 1 This is a flow chart of the overall method provided in Example 1 of the present invention.

[0036] Figure 2 This is a timing diagram of the overall method provided in Example 1 of the present invention.

[0037] Figure 3 This is a timing diagram of the dynamic weight allocation strategy provided in Example 1 of the present invention.

[0038] Figure 4 This is an algorithm timing diagram of step 2 provided in embodiment 1 of the present invention.

[0039] Figure 5 This is a flowchart of the overall algorithm provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0041] Example 1

[0042] This embodiment discloses an AI-based cold chain warehouse drone obstacle avoidance and path planning inventory method.

[0043] In the existing cold chain warehouse inventory, due to the lack of intuitive environmental monitoring methods, it is difficult to fully grasp the real-time status of the warehouse, resulting in low inventory efficiency, certain safety hazards, and inability to adapt to changes in the dynamic environment.

[0044] In order to solve the above problems, a cold chain warehouse drone obstacle avoidance and path planning inventory method based on AI intelligence is disclosed in this embodiment. This method arranges various types of sensors in the target cold chain warehouse, integrates these sensors into a unified sensor cluster through the edge gateway, and configures a temperature-dominated perception hierarchy dynamic weight allocation strategy in the edge gateway. The weights of different types of sensors are dynamically adjusted according to the dynamic changes of the temperature field, thereby optimizing the data fusion effect of the sensor cluster and improving the accuracy and reliability of environmental perception. At the same time, by constructing a digital twin model of the target cold chain warehouse in the cloud, the backend management personnel can intuitively monitor the environmental changes of the warehouse. In addition, the method also proposes an intelligent inventory path planning algorithm, which can ensure that drones can perform inventory operations efficiently and safely in a complex cold chain warehouse environment, avoid collisions in abnormal areas, and adapt to changes in the dynamic environment.

[0045] The solution in this embodiment realizes autonomous inventory and real-time digital twin modeling of drones in low-temperature and complex environments through a layered architecture.

[0046] Specifically, the solutions in this application can be roughly divided into 4 levels:

[0047] The perception layer, built from a variety of sensors, is used for environmental perception in cold chain warehouses.

[0048] The decision-making layer located in the cloud data center is built by a path planning algorithm. The decision-making layer realizes local obstacle avoidance based on the sensor data of the perception layer and combines the AI ​​intelligent algorithm with the shelf topology semantics to output the drone obstacle avoidance and inventory path plan.

[0049] The twin layer located in the cloud data center builds a digital twin model of the target cold chain warehouse based on the digital twin technology. The twin layer is used to realize real-time reconstruction of the digital twin model based on the data of the perception layer and the decision-making layer, based on the 3D dynamic map of point cloud registration, and integrating RFID shelf coding and temperature field data. It can display the specific situation of the target cold chain warehouse in real time, which is convenient for back-end management personnel to monitor.

[0050] The execution layer is used to receive the inventory path plan sent by the path planning algorithm, operate the drone to complete the path inventory operation, and send the real-time collected information to the twin layer to realize real-time data update and reconstruction.

[0051] This application innovatively integrates multiple advanced technologies to optimize and improve the existing cold chain warehouse management system from multiple levels such as environmental perception, environmental monitoring and operation planning, and is expected to significantly improve the overall level of cold chain warehouse management.

[0052] Figure 1 : shows the overall method flow chart of this embodiment, Figure 2 The overall method timing diagram provided by this embodiment is shown. Figure 1 It can be seen that this embodiment includes the following steps:

[0053] Step 1: Arrange various types of sensors in the target cold chain warehouse to sense the environmental changes in the cold chain warehouse. Integrate various types of sensors into a unified sensor cluster through the edge gateway, pre-process the data collected by the sensors in the edge gateway, and send the processed data to the cloud database.

[0054] Specifically, in this embodiment, the various types of sensors include temperature sensors, humidity sensors, 3D lidar sensors, multi-spectral ToF sensors, RGB-D camera sensors, long-wave infrared thermal imager sensors, millimeter-wave radar array sensors, and UWB / RFID positioning tags.

[0055] Among them, temperature sensors, humidity sensors, multispectral ToF sensors, and RGBD camera sensors are installed at a certain distance on the shelves of the cold chain warehouse. Temperature sensors and humidity sensors are used to detect changes in temperature and humidity in the cold chain warehouse. Multispectral ToF sensors are used to accurately locate shelf spacing. RGBD camera sensors are used for near-field object recognition and shelf code OCR analysis.

[0056] 3D LiDAR sensors, millimeter wave radar arrays, and long-wave infrared thermal imagers are installed on the beams of the cold chain warehouse. 3D LiDAR sensors are used to detect major obstacles (non-moving or slow-moving obstacles), and millimeter wave radar arrays are used for dynamic obstacle tracking. Long-wave infrared thermal imagers are used for temperature gradient field modeling and can also be used to detect low-temperature risks such as hidden icicles.

[0057] It should be noted that, considering that the temperature of the cold chain warehouse is very important, in this embodiment, the temperature sensor can be specially processed during the layout, and the edge gateway can pre-process the data collected by other sensors with the data of the temperature sensor as the core. Specifically, the pre-processing of the data collected by the sensor in the edge gateway can include:

[0058] By deploying multiple ZigBee wireless temperature measurement nodes on each row of shelves, each ZigBee wireless temperature measurement node is a temperature field grid, and all ZigBee wireless temperature measurement nodes together constitute a temperature field grid covering the entire cold chain warehouse. The specific size of the grid can be set according to actual conditions. In order to better illustrate the solution of this embodiment, a 1m×1m×1m grid layout is adopted.

[0059] The edge gateway is configured with a temperature-dominated perception-level dynamic weight allocation strategy. This strategy implements dynamic weight adjustment by building a temperature-sensitive confidence evaluation system based on the temperature field grid data collected by the ZigBee wireless temperature measurement node. The dynamic weight allocation strategy uses the temperature data collected by the ZigBee wireless temperature measurement node in the temperature field as the basic data for calculation, and adjusts the weights of different sensors based on the dynamic changes of the temperature field, thereby achieving more efficient and accurate environmental perception. Its core is to dynamically adjust the trust and weight of different types of sensors according to temperature changes (such as the gradient and change rate of the temperature field), thereby optimizing the data fusion effect of the sensor cluster.

[0060] Specifically, Figure 3 The timing diagram of the dynamic weight allocation strategy in this embodiment is shown. Figure 3 As can be seen from the figure, the dynamic weight allocation strategy includes the following:

[0061] 1) Based on the collected temperature data, calculate the temperature gradient and temperature change rate to evaluate the dynamic changes of the temperature field.

[0062] Specifically, the temperature gradient indicates the direction and rate of temperature change, which is the rate of change of temperature in space. For a temperature field T(x, y, z) in a three-dimensional space, its temperature gradient can be expressed as:

[0063] ,

[0064] in, is the Laplace operator, which is used to indicate that the temperature gradient is the rate of change of the temperature field, indicating the direction and rate of temperature change; is the temperature field in three-dimensional space; is the rate of change of temperature in the x direction, is the rate of change of temperature in the y direction, is the rate of change of temperature in the z direction.

[0065] It should be noted that the temperature gradient calculation method may vary depending on the measurement equipment and data source. For example, the temperature gradient may be calculated using a discrete difference method, a gradient estimation method, or a weighted average method.

[0066] In this embodiment, the temperature data collected by the ZigBee wireless temperature measurement node is usually discrete data. In this case, the temperature gradient can be approximately calculated by the finite difference method.

[0067] For example, assuming we have the values ​​of the temperature field T(x, y, z) at discrete points in space, then the temperature gradient can be calculated as follows:

[0068] The rate of change in the x direction is:

[0069] ,

[0070] The rate of change in the y direction is:

[0071] ,

[0072] The rate of change in the z direction is:

[0073] ,

[0074] in, , and are the distances between adjacent measurement points in the space with different coordinates in the spatial coordinate system.

[0075] It should be noted that the temperature gradient The rate and direction of temperature change in the cold chain warehouse in space are described. In practical applications, different methods can be used for temperature gradient according to different scenarios and sensor arrangements. The finite difference method disclosed in this embodiment is only used as an explanation and cannot be considered as a limitation of the invention in the present invention.

[0076] 2) According to the calculated temperature gradient and change rate, the confidence of each area is calculated to provide a basis for dynamically adjusting the sensor weight. Specifically, the confidence can be calculated by the following formula:

[0077] ,

[0078] in, is the confidence level, is the weight coefficient used to adjust the contribution of temperature gradient to confidence, is the modulus of the temperature gradient, To adjust the weight coefficient of the temperature change rate contribution to the confidence, is the absolute value of the temperature change rate.

[0079] 3) At the same time, determine whether the current temperature change is drastic based on the temperature gradient and the rate of change. If the temperature change is drastic, enter the stage of adjusting the sensor weight; if the temperature change is not drastic, keep the current weight unchanged.

[0080] 4) In the sensor weight adjustment stage, the sensor weight is dynamically adjusted according to the confidence of each area calculated.

[0081] First, the basic weight of the i-th sensor of the same type is calculated by the following formula:

[0082] ,

[0083] in, is the basic weight of the i-th sensor of the same type, is an exponential function; is the priority coefficient of the i-th sensor, which is used to reflect the importance of different sensors in the system. This coefficient can be adjusted according to the actual situation and is based on the subjective evaluation of the priority of this type of sensor in the target cold chain warehouse; is the influence coefficient of temperature on the performance of sensor i. N is the total number of all sensors of the same type, is the overall priority coefficient of sensors of the same type, is the influence coefficient of the same type of sensor. j represents a specific sensor, and i represents the i-th sensor in the specific sensor.

[0084] It should be noted that the above formula is based on the idea of ​​weighted averaging, and dynamically adjusts the weight of each sensor through exponential functions and normalization. The denominator is the exponential weighted sum of all sensors of the same type, which is used for normalization. In this formula, the exponential function (exp) is used to ensure that the weight is always non-negative. Since the exponential function grows rapidly with the increase of input values, the weight distribution is very sensitive to the difference in input values, thereby highlighting those sensors with better performance. In the formula, Used to amplify the difference in the effect of temperature on sensor performance. It is used to represent the influence coefficient of temperature on the performance of the i-th type sensor. This coefficient reflects the performance change of the sensor under different temperature conditions. The temperature gradient and the rate of temperature change need to be considered when constructing It is used to characterize the effect of the rate of temperature change in space on the type of sensor. In places with large temperature gradients, a certain type of sensor may require higher responsiveness. It is used to characterize the effect of the rate of change of temperature over time on the type of sensor. In places where the rate of change is fast, the performance of a certain type of sensor may be more affected. For example: a possible The construction method is: , where a i and b i The performance of this type of sensor is affected by factors related to temperature gradient and rate of temperature change.

[0085] After obtaining the basic weight of the sensor through the above calculation, the confidence is combined with the basic weight to obtain the time-varying weight so as to dynamically adjust the weight of each sensor. The time-varying weight is calculated by the following formula:

[0086] ,

[0087] in, is the time-varying weight of sensor i; is the confidence of sensor i at the current moment, indicating the data credibility of the sensor in an area or environment with large temperature changes.

[0088] It should be noted that, through time-varying weights, the contribution of the data collected by the sensor can be dynamically adjusted according to the real-time temperature changes. When the confidence is high, the weight of the corresponding sensor increases; when the confidence is low, the weight of the corresponding sensor decreases. Since the weights of different sensors are dynamically adjusted, they can better reflect the changes in the current environment and improve the accuracy of the overall sensor data fusion. Sensor data with high confidence is given a higher weight, which enhances the monitoring effect of key areas. In areas where the temperature changes slowly, the weight of the sensor is low, which can effectively reduce the impact of data errors caused by sensor noise on the entire system, thereby optimizing the data fusion effect. In other words, the time-varying weight achieves real-time response to temperature changes by dynamically adjusting the contribution of the sensor, and optimizes the data fusion effect of the sensor cluster. This enables the perception layer constructed by multiple sensors to more flexibly and accurately reflect and respond to environmental changes, thereby improving the performance and reliability of the overall system.

[0089] Step 2: Build a digital twin model of the target cold chain warehouse and an intelligent inventory path planning algorithm in the cloud database.

[0090] The cloud database receives the sensor data sent by the edge gateway, builds a sensor database based on the received data, and maps the data in the sensor database to the digital twin model, allowing back-end managers to intuitively monitor environmental changes in the cold chain warehouse.

[0091] The intelligent inventory path planning algorithm outputs the drone obstacle avoidance-inventory path plan based on the sensor data.

[0092] Specifically, in this embodiment, the intelligent inventory path planning algorithm is a multi-level, dynamic path planning algorithm based on the A* algorithm, and its purpose is to ensure that the drone can perform inventory tasks efficiently and safely in a complex cold chain warehouse environment.

[0093] By integrating information from different sensors, it provides comprehensive perception of the environment. In particular, the temperature and humidity data of the sensors monitor the temperature and humidity changes in the warehouse in real time to ensure that the environmental requirements of the cold chain warehouse are taken into account when planning the path. And through global path planning, a preliminary path is generated and the path is locally optimized. Through dynamic path adjustment and spiral maneuvers, it ensures that the drone can adapt to dynamic environmental changes and avoid collisions with abnormal areas. Specifically, it includes the following:

[0094] 1) First, the environment of the cold chain warehouse is discretized and converted into a discretized model consisting of temperature-space joint voxels. Voxel is a pixel unit in a three-dimensional space, which represents a small cube in space. In this model, each voxel contains information related to the warehouse environment, especially temperature and humidity sensor data. In this embodiment, the voxel can be represented as:

[0095] ,

[0096] in, is the identifier of the voxel, a, b, c represent the index of the voxel in the three dimensions of x, y, and z in the spatial coordinate system respectively. Through these indexes, the position of each voxel in the cold chain warehouse can be identified. Each voxel represents a discrete spatial area. In this embodiment, a resolution of 1m is used to divide the entire space. A resolution of 1m means that the side length of each voxel is 1 meter, or each voxel occupies a cubic space of 1m×1m×1m. x, y, z are spatial coordinates, indicating the position of the voxel in three-dimensional space, and T is the temperature value in the voxel in degrees Celsius (℃). One of the core requirements of cold chain warehouses is temperature control, so each voxel has a temperature value to indicate the temperature at that spatial position. Temperature data is also important for drone inventory path planning, because drones need to focus on patrolling areas with extreme temperature changes to ensure the safety of goods. is the gradient of the temperature value in this voxel. is the confidence of the sensor data contained in the voxel (that is, the data obtained by the confidence calculation in step 1).

[0097] 2) Based on the discretization model, the path of the UAV is optimized through a multi-constraint optimization objective function according to the relevant information provided in the discretization model.

[0098] Specifically, the multi-constraint optimization objective function includes:

[0099] ,

[0100] Among them, π is the optimization path, is the temperature exposure term, is the time cost item, is the sensor risk item, is the weight coefficient of the time cost item, are the weight coefficients of the sensor risk term. These two weight coefficients are used to control the influence of each constraint on the optimization path.

[0101] It should be noted that, in this embodiment, the temperature exposure term can be expressed by the following formula:

[0102] ,

[0103] Where k is the exponential decay factor, is the temperature value of a certain position s on the path, T ref is the reference temperature, which represents the ideal temperature state of the cold chain warehouse. The degree to which the temperature on the path deviates from the reference temperature will affect the size of the penalty term.

[0104] It should be noted that in this formula It is an exponential term, which is used to indicate that when the temperature deviates from the reference temperature, it means that the temperature exposure on the path will increase. In order to ensure the safety of cold chain goods, it is necessary to focus on checking this point. For the temperature gradient term, areas with drastic temperature changes usually cause problems for goods in cold storage, so drones should try to pass through these areas.

[0105] The time cost term can be expressed as follows:

[0106] ,

[0107] Among them, the total path length refers to the total distance of the drone path planning, that is, the sum of the spatial distances between all s points on the path. The average cruising speed of the drone refers to the average flight speed of the drone when performing a mission.

[0108] The sensor risk term can be expressed as follows:

[0109] ,

[0110] in, represents the sensor confidence at a certain position s in the path.

[0111] 3) A multi-constraint optimization objective function is used to replace the cost function of the A* algorithm. The cost function f (n) of the A* algorithm is redefined to comprehensively consider temperature exposure, time cost, and sensor risk. The A* algorithm is used to find an optimal path that can ensure the safety of the goods and complete the task efficiently.

[0112] ,

[0113] in, is the new cost function, is the actual cost from the starting point to the current node n, which can include the flight distance and time cost of the drone. For the A* algorithm, it can usually be represented by the flight path length. optimized(n) is a new heuristic function used to estimate the cost from the current node to the target node. This heuristic function not only considers the spatial distance, but also comprehensively considers multiple constraints such as temperature exposure, time cost and sensor risk.

[0114] Specifically, in this embodiment, the heuristic function needs to comprehensively consider:

[0115] Temperature exposure term: The time on the path where the vehicle may be exposed to different temperature areas. To avoid high or low temperature areas, the potential risk of temperature exposure on the path can be considered in the heuristic function. For example, the temperature gradient on the possible path can be weighted to avoid areas with abnormal temperatures.

[0116] Time cost term: This part can be calculated by estimating the flight time from the current node to the target node. If there is a longer flight time on the path, the value of the heuristic function will increase.

[0117] Sensor risk item: The risk of sensors (such as unreliable data or failure) can affect the choice of path, so sensor confidence needs to be considered. If the sensor data quality in some areas is poor, the path selection needs to be adjusted by increasing the sensor risk.

[0118] In summary, in this embodiment, the heuristic function may be in the form of:

[0119] ,

[0120] in, , , is the weight coefficient, which is used to balance the importance of different factors; d (n) is the spatial distance from node n to the target node; is the estimated temperature exposure at node n, is the risk estimate of the sensor at node n.

[0121] The path search process of the A* algorithm after replacing the cost function of the A* algorithm with the multi-constrained optimization objective function is as follows:

[0122] Initialize the open list and the closed list, starting from = 0, the heuristic function is initialized based on the estimate of the target path.

[0123] Starting from the current node, expand its neighboring nodes. For each neighboring node, calculate:

[0124] , and select the node with the minimum cost for expansion based on the cost.

[0125] When expanding nodes, check whether the path encounters obstacles (such as shelves, walls, etc.) or whether there are temperature anomalies in certain areas.

[0126] Continue to iterate and expand the path until the target node is found. Each time you expand, consider the cost of the current path , and select the path with the minimum cost for expansion.

[0127] The A* algorithm terminates when it finds the target node and returns an optimal path from the starting point to the target node. In this optimal path, the cost of each edge optimizes the temperature exposure, time cost, and sensor risk as much as possible. In order to better illustrate the data timing calculation process in step 2, the algorithm timing diagram of step 2 is drawn as follows Figure 4 shown.

[0128] Step 3: The cloud sends the path plan output by the intelligent inventory path planning algorithm to the drone terminal and the digital twin model at the same time.

[0129] Step 4: The drone terminal completes the inventory task according to the path plan, and the digital twin model updates the digital twin model in real time according to the path plan and the data fed back by the drone terminal. In order to better illustrate the algorithm calculation process in this embodiment, the overall algorithm flow chart is drawn as follows: Figure 5 shown.

[0130] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An AI-based cold chain warehouse drone obstacle avoidance and path planning inventory method, characterized in that: The path planning inventory method comprises: S100: Arrange different types of sensors in the cold chain warehouse for sensing environmental changes in the cold chain warehouse. The edge gateway integrates different types of sensors into a unified sensor cluster, pre-processes the collected data, and sends the processed data to the cloud database; S200, builds a digital twin model of the target cold chain warehouse in the cloud database, and an intelligent inventory path planning algorithm, The cloud database builds a sensor database based on the received data and maps the data in the sensor database to the digital twin model. The intelligent inventory path planning algorithm outputs the obstacle avoidance-inventory path plan for the drone based on the sensor data; S300, the cloud sends the path plan output by the intelligent inventory path planning algorithm to the drone terminal and the digital twin model at the same time; S400 and the drone terminal complete the inventory task according to the path plan, while the digital twin model updates the digital twin model in real time based on the path plan and the data fed back by the drone terminal.

2. The AI-based cold chain warehouse drone obstacle avoidance and path planning inventory method according to claim 1 is characterized in that: The different types of sensors include temperature sensors, humidity sensors, 3D lidar sensors, multi-spectral ToF sensors, RGB-D camera sensors, long-wave infrared thermal imager sensors, millimeter-wave radar array sensors, and UWB / RFID positioning tags.

3. The AI-based cold chain warehouse drone obstacle avoidance and path planning inventory method according to claim 1 is characterized in that: The pre-processing comprises: S110, deploying multiple ZigBee wireless temperature measurement nodes on each row of shelves, each ZigBee wireless temperature measurement node being a temperature field grid; S120, the perception-level dynamic weight allocation strategy in the edge gateway builds a temperature-sensitive confidence evaluation system according to the number of temperature field grids collected by the ZigBee wireless temperature measurement node to achieve dynamic weight adjustment.

4. The AI-based cold chain warehouse drone obstacle avoidance and path planning inventory method according to claim 3 is characterized in that: The dynamic weight allocation strategy includes the following steps: S121. Calculate the temperature gradient and the temperature change rate according to the collected temperature data to evaluate the dynamic change of the temperature field. The temperature gradient is expressed by the following formula: ， in, is the Laplace operator, is the temperature field in three-dimensional space; is the rate of change of temperature in the x direction, is the rate of change of temperature in the y direction, is the rate of change of temperature in the z direction; S123. Calculate the confidence of each area according to the calculated temperature gradient and change rate. The confidence is calculated by the following formula: ， in, is the confidence level, is the weight coefficient used to adjust the contribution of temperature gradient to confidence, is the modulus of the temperature gradient, To adjust the weight coefficient of the temperature change rate contribution to the confidence, is the absolute value of the temperature change rate; S124: Determine whether the current temperature change is drastic based on the temperature gradient and the rate of change. If the temperature change is drastic, enter the sensor weight adjustment stage. If the temperature change is not drastic, keep the current weight unchanged; S125. In the sensor weight adjustment stage, the sensor weight is dynamically adjusted according to the confidence of each area. The weight is a time-varying weight and is calculated by the following formula: ， in, is the time-varying weight of sensor i; is the confidence of sensor i at the current moment, is the basic weight of the i-th sensor of the same type.

5. The AI-based cold chain warehouse drone obstacle avoidance and path planning inventory method according to claim 4 is characterized in that: The basic weight is calculated by the following formula: ， in, is the basic weight of the i-th sensor of the same type, is an exponential function; is the priority coefficient of the i-th sensor; is the influence coefficient of temperature on the performance of sensor i; N is the total number of all sensors of the same type, is the overall priority coefficient of sensors of the same type, is the influence coefficient of the same type of sensor, j represents the same type of sensor, and i represents the i-th sensor in the same type of sensor.

6. The AI-based cold chain warehouse drone obstacle avoidance and path planning inventory method according to claim 1 is characterized in that: The intelligent inventory path planning algorithm is constructed based on the A* algorithm and includes the following steps: S210, converting the environment of the cold chain warehouse into a discretized model consisting of temperature-space joint voxels, wherein the temperature-space joint voxels are represented as: ， in, is the identifier of the voxel, a, b, c represent the index of the voxel in the three dimensions of x, y, and z in the spatial coordinate system, respectively. x, y, and z are spatial coordinates, indicating the position of the voxel in three-dimensional space. T is the temperature value in the voxel. is the gradient of the temperature value in the voxel, is the confidence of the sensor data contained in the voxel; S220. Optimize the path of the UAV according to the relevant information provided in the discretization model and in combination with a multi-constraint optimization objective function, wherein the multi-constraint optimization objective function includes: ， Among them, π is the optimization path, is the temperature exposure term, is the time cost item, is the sensor risk item, is the weight coefficient of the time cost item, are the weight coefficients of the sensor risk item. These two weight coefficients are used to control the influence of each constraint on the optimization path; S230, replacing the cost function of the A* algorithm with a multi-constraint optimization objective function, redefining the cost function f (n) of the A* algorithm so that it can comprehensively consider temperature exposure, time cost and sensor risk, and finally generating an optimal path through the A* algorithm.

7. The AI-based cold chain warehouse drone obstacle avoidance and path planning inventory method according to claim 6 is characterized in that: The method of replacing the cost function of the A* algorithm by the multi-constraint optimization objective function comprises the following steps: S231, initialize the open list and closed list, the starting point =0, the heuristic function is initialized according to the estimate of the target path; S232. Starting from the current node, expand its neighboring nodes. For each neighboring node, calculate: ， in, is the new cost function, is the actual cost from the starting point to the current node n, h optimized (n) is the new heuristic function, Select the node with the minimum cost to expand according to the cost. When expanding the node, check whether the path encounters obstacles or whether there is temperature anomaly in the area; S233, continue to iterate and expand the path until the target node is found. Each time the path is expanded, the cost of the current path is considered. , and select the path with the minimum cost for expansion.

8. The AI-based cold chain warehouse drone obstacle avoidance and path planning inventory method according to claim 7 is characterized in that: The new heuristic function is expressed as follows: ， in, , , is the weight coefficient, which is used to balance the importance of different factors; d (n) is the spatial distance from node n to the target node; is the estimated temperature exposure at node n, is the risk estimate of the sensor at node n.

9. An AI-based cold chain warehouse drone obstacle avoidance and path planning inventory system, characterized in that: The AI-based cold chain warehouse drone obstacle avoidance and path planning inventory system includes: processor; A memory storing a computer program, which, when executed by a processor, implements the cold chain warehouse drone obstacle avoidance and path planning inventory method based on AI intelligence as described in any one of claims 1 to 8.

Images